#2 Gemini 3 Flash Preview
medium- Gharama
- $0.010
- Muda
- 17.9s
- Tokeni
- 3,236 tok
AI BENCHY Compare
Muhtasari
Gemini 3 Flash Preview (medium) inaongoza kwa average score: 9.6 vs 7.7. KAT-Coder-Pro V2.5 (high) ina gharama ya chini ya benchmark: $0.246 vs $0.667. KAT-Coder-Pro V2.5 (high) ni ya haraka zaidi: 12.30s vs 18.64s, na pass rates 98.4% vs 63.5%.
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-07-14
| Kipimo | Gemini 3 Flash Preview Gemini 3 Flash Preview medium | KAT-Coder-Pro V2.5 KAT-Coder-Pro V2.5 high |
|---|---|---|
| Alama | 9.6 | 7.7 |
| Nafasi | #2 | #53 |
| Uaminifu | 10.0 | 10.0 |
| Uthabiti | 9.7 | 8.1 |
| Majaribio sahihi | ||
| Kiwango cha kupita kwa kila jaribio | 98.4% | 63.5% |
| Majaribio yasiyo thabiti | 1 | 5 |
| Jumla ya uendeshaji | 63 | 63 |
| Gharama kwa matokeo | 3.335 | 2.228 |
| Jumla ya gharama | $0.667 | $0.246 |
| Bei ya ingizo | $0.500 / 1M | $0.740 / 1M |
| Bei ya toleo | $3.000 / 1M | $2.960 / 1M |
| Jumla ya tokeni za ingizo | 37,017 | 42,750 |
| Tokeni za matokeo | 2,006 | 2,509 |
| Tokeni za hoja | 214,153 | 69,594 |
| Muda wa majibu (wastani) | 18.64s | 12.30s |
| Muda wa majibu (upeo) | 117.26s | 95.65s |
| Muda wa majibu (jumla) | 391.35s | 258.34s |
Onyesho la kizazi
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
| Uandishi wa msimbo | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 8.6 | 7.6 | 88.9% | 1 | 84.40s | 8,122 | 462 | 161,084 | |
| KAT-Coder-Pro V2.5 | 6.4 | 7.9 | 44.4% | 1 | 22.00s | 7,893 | 422 | 20,461 |
Badilisha jozi ya ulinganisho